storm.trident.testing.FixedBatchSpout Java Examples

public static StormTopology buildTopology(LocalDRPC drpc) {
  FixedBatchSpout spout = new FixedBatchSpout(new Fields("sentence"), 3, new Values("the cow jumped over the moon"),
      new Values("the man went to the store and bought some candy"), new Values("four score and seven years ago"),
      new Values("how many apples can you eat"), new Values("to be or not to be the person"));
  spout.setCycle(true);

  TridentTopology topology = new TridentTopology();
  TridentState wordCounts = topology.newStream("spout1", spout).parallelismHint(16).each(new Fields("sentence"),
      new Split(), new Fields("word")).groupBy(new Fields("word")).persistentAggregate(new MemoryMapState.Factory(),
      new Count(), new Fields("count")).parallelismHint(16);

  topology.newDRPCStream("words", drpc).each(new Fields("args"), new Split(), new Fields("word")).groupBy(new Fields(
      "word")).stateQuery(wordCounts, new Fields("word"), new MapGet(), new Fields("count")).each(new Fields("count"),
      new FilterNull()).aggregate(new Fields("count"), new Sum(), new Fields("sum"));
  return topology.build();
}
 

public StormTopology getTopology(Config config) {

        this.spout = new FixedBatchSpout(new Fields("sentence"), 20,
                new Values("one two"),
                new Values("two three"),
                new Values("three four"),
                new Values("four five"),
                new Values("five six")
        );


        TridentTopology trident = new TridentTopology();

        trident.newStream("wordcount", spout).name("sentence").parallelismHint(1).shuffle()
                .each(new Fields("sentence"), new Split(), new Fields("word"))
                .parallelismHint(1)
                .groupBy(new Fields("word"))
                .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"))
                .parallelismHint(1);
        return trident.build();
    }
 

@Override
protected StormTopology buildTopology() {
    FixedBatchSpout spout = new FixedBatchSpout(new Fields("sentence"), 3,
            new Values("the cow jumped over the moon"),
            new Values("the man went to the store and bought some candy"),
            new Values("four score and seven years ago"),
            new Values("how many apples can you eat"),
            new Values("to be or not to be the person"));
    spout.setCycle(true);

    ESIndexState.Factory<Tweet> factory = new ESIndexState.Factory<>(getLocalClient(), Tweet.class);
    TridentTopology topology = new TridentTopology();

    TridentState state = topology.newStream("tweets", spout)
            .partitionPersist(factory, new Fields("sentence"), new ESIndexUpdater(new MyTridentTupleMapper()));

    topology.newDRPCStream("search", drpc)
            .each(new Fields("args"), new ExtractSearchArgs(), new Fields("query", "indices", "types"))
            .groupBy(new Fields("query", "indices", "types"))
            .stateQuery(state, new Fields("query", "indices", "types"), new QuerySearchIndexQuery(), new Fields("tweet"))
            .each(new Fields("tweet"), new FilterNull())
            .each(new Fields("tweet"), new CreateJson(), new Fields("json"))
            .project(new Fields("json"));

    return topology.build();
}
 

public static StormTopology buildTopology(LocalDRPC drpc) {
    FixedBatchSpout spout = new FixedBatchSpout(new Fields("sentence"), 3,
            new Values("the cow jumped over the moon"),
            new Values("the man went to the store and bought some candy"),
            new Values("four score and seven years ago"), new Values("how many apples can you eat"),
            new Values("to be or not to be the person"));
    spout.setCycle(true);
    
    TridentTopology topology = new TridentTopology();
    TridentState wordCounts = topology.newStream("spout1", spout).parallelismHint(16)
            .each(new Fields("sentence"), new Split(), new Fields("word")).groupBy(new Fields("word"))
            .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"))
            .parallelismHint(16);
            
    topology.newDRPCStream("words", drpc).each(new Fields("args"), new Split(), new Fields("word"))
            .groupBy(new Fields("word"))
            .stateQuery(wordCounts, new Fields("word"), new MapGet(), new Fields("count"))
            .each(new Fields("count"), new FilterNull())
            .aggregate(new Fields("count"), new Sum(), new Fields("sum"));
    return topology.build();
}
 

public static StormTopology buildTopology(LocalDRPC drpc) {
    FixedBatchSpout spout = new FixedBatchSpout(new Fields("word"), 3, new Values("the cow jumped over the moon"),
            new Values("the man went to the store and bought some candy"),
            new Values("four score and seven years ago"), new Values("how many apples can you eat"),
            new Values("to be or not to be the person"));
    spout.setCycle(true);
    
    TridentTopology topology = new TridentTopology();
    TridentState wordCounts = topology.newStream("spout1", spout).parallelismHint(16).flatMap(split).map(toUpper)
            .filter(theFilter).peek(new Consumer() {
                @Override
                public void accept(TridentTuple input) {
                    System.out.println(input.getString(0));
                }
            }).groupBy(new Fields("word"))
            .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"))
            .parallelismHint(16);
            
    topology.newDRPCStream("words", drpc).flatMap(split).groupBy(new Fields("args"))
            .stateQuery(wordCounts, new Fields("args"), new MapGet(), new Fields("count")).filter(new FilterNull())
            .aggregate(new Fields("count"), new Sum(), new Fields("sum"));
    return topology.build();
}
 

public static StormTopology buildTopology(WindowsStoreFactory windowStore, WindowConfig windowConfig)
        throws Exception {
    FixedBatchSpout spout = new FixedBatchSpout(new Fields("sentence"), 3,
            new Values("the cow jumped over the moon"),
            new Values("the man went to the store and bought some candy"),
            new Values("four score and seven years ago"), new Values("how many apples can you eat"),
            new Values("to be or not to be the person"));
    spout.setCycle(true);
    
    TridentTopology topology = new TridentTopology();
    
    Stream stream = topology.newStream("spout1", spout).parallelismHint(16)
            .each(new Fields("sentence"), new Split(), new Fields("word"))
            .window(windowConfig, windowStore, new Fields("word"), new CountAsAggregator(), new Fields("count"))
            .peek(new Consumer() {
                @Override
                public void accept(TridentTuple input) {
                    LOG.info("Received tuple: [{}]", input);
                }
            });
            
    return topology.build();
}
 

/**
 * Creates a topology which demonstrates min/max operations on tuples of
 * stream which contain vehicle and driver fields with values
 * {@link TridentMinMaxOfDevicesTopology.Vehicle} and
 * {@link TridentMinMaxOfDevicesTopology.Driver} respectively.
 */
public static StormTopology buildVehiclesTopology() {
    Fields driverField = new Fields(Driver.FIELD_NAME);
    Fields vehicleField = new Fields(Vehicle.FIELD_NAME);
    Fields allFields = new Fields(Vehicle.FIELD_NAME, Driver.FIELD_NAME);
    
    FixedBatchSpout spout = new FixedBatchSpout(allFields, 10, Vehicle.generateVehicles(20));
    spout.setCycle(true);
    
    TridentTopology topology = new TridentTopology();
    Stream vehiclesStream = topology.newStream("spout1", spout).each(allFields, new Debug("##### vehicles"));
    
    Stream slowVehiclesStream = vehiclesStream.min(new SpeedComparator()).each(vehicleField,
            new Debug("#### slowest vehicle"));
            
    Stream slowDriversStream = slowVehiclesStream.project(driverField).each(driverField,
            new Debug("##### slowest driver"));
            
    vehiclesStream.max(new SpeedComparator()).each(vehicleField, new Debug("#### fastest vehicle"))
            .project(driverField).each(driverField, new Debug("##### fastest driver"));
            
    vehiclesStream.max(new EfficiencyComparator()).each(vehicleField, new Debug("#### efficient vehicle"));
    
    return topology.build();
}
 

public StormTopology getTopology(Config config) {

        this.spout = new FixedBatchSpout(new Fields("sentence"), 20,
                new Values("one two"),
                new Values("two three"),
                new Values("three four"),
                new Values("four five"),
                new Values("five six")
        );


        TridentTopology trident = new TridentTopology();

        trident.newStream("wordcount", spout).name("sentence").parallelismHint(1).shuffle()
                .each(new Fields("sentence"), new Split(), new Fields("word"))
                .parallelismHint(1)
                .groupBy(new Fields("word"))
                .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"))
                .parallelismHint(1);
        return trident.build();
    }
 

@Override
public StormTopology buildTopology( ) {
    ESIndexMapState.Factory<Tweet> state = ESIndexMapState.nonTransactional(getLocalClient(), Tweet.class);

    FixedBatchSpout spout = new FixedBatchSpout(new Fields("sentence"), 3,
            new Values("the cow jumped over the moon"),
            new Values("the man went to the store and bought some candy"),
            new Values("four score and seven years ago"),
            new Values("how many apples can you eat"),
            new Values("to be or not to be the person"));
    spout.setCycle(true);

    TridentTopology topology = new TridentTopology();

    TridentState staticState = topology.newStaticState(new ESIndexState.Factory<>(getLocalClient(), Tweet.class));

    topology.newStream("tweets", spout)
                    .each(new Fields("sentence"), new DocumentBuilder(), new Fields("document"))
                    .each(new Fields("document"), new ExtractDocumentInfo(), new Fields("id", "index", "type"))
                    .groupBy(new Fields("index", "type", "id"))
                    .persistentAggregate(state, new Fields("document"), new TweetBuilder(), new Fields("tweet"))
                    .parallelismHint(1);

    topology.newDRPCStream("search", drpc)
            .each(new Fields("args"), new ExtractSearchArgs(), new Fields("query", "indices", "types"))
            .groupBy(new Fields("query", "indices", "types"))
            .stateQuery(staticState, new Fields("query", "indices", "types"), new QuerySearchIndexQuery(), new Fields("tweet"))
            .each(new Fields("tweet"), new FilterNull())
            .each(new Fields("tweet"), new CreateJson(), new Fields("json"))
            .project(new Fields("json"));

    return topology.build();
}
 

@SuppressWarnings("unchecked")
public static StormTopology buildWordCountAndSourceTopology(LocalDRPC drpc) {
    LOG.info("Building topology.");
    TridentTopology topology = new TridentTopology();

    String source1 = "spout1";
    String source2 = "spout2";
    FixedBatchSpout spout1 = new FixedBatchSpout(new Fields("sentence", "source"), 3,
            new Values("the cow jumped over the moon", source1),
            new Values("the man went to the store and bought some candy", source1),
            new Values("four score and four years ago", source2),
            new Values("how much wood can a wood chuck chuck", source2));
    spout1.setCycle(true);

    TridentState wordCounts =
            topology.newStream("spout1", spout1)
                    .each(new Fields("sentence"), new Split(), new Fields("word"))
                    .groupBy(new Fields("word", "source"))
                    .persistentAggregate(CassandraCqlMapState.nonTransactional(new WordCountAndSourceMapper()),
                            new IntegerCount(), new Fields("count"))
                    .parallelismHint(6);

    topology.newDRPCStream("words", drpc)
            .each(new Fields("args"), new Split(), new Fields("word"))
            .groupBy(new Fields("word"))
            .stateQuery(wordCounts, new Fields("word"), new MapGet(), new Fields("count"))
            .each(new Fields("count"), new FilterNull())
            .aggregate(new Fields("count"), new Sum(), new Fields("sum"));

    return topology.build();
}
 

/**
 * Creates a topology which demonstrates min/max operations on tuples of
 * stream which contain vehicle and driver fields with values
 * {@link TridentMinMaxOfVehiclesTopology.Vehicle} and
 * {@link TridentMinMaxOfVehiclesTopology.Driver} respectively.
 */
public static StormTopology buildVehiclesTopology() {
    Fields driverField = new Fields(Driver.FIELD_NAME);
    Fields vehicleField = new Fields(Vehicle.FIELD_NAME);
    Fields allFields = new Fields(Vehicle.FIELD_NAME, Driver.FIELD_NAME);
    
    FixedBatchSpout spout = new FixedBatchSpout(allFields, 10, Vehicle.generateVehicles(20));
    spout.setCycle(true);
    
    TridentTopology topology = new TridentTopology();
    Stream vehiclesStream = topology.newStream("spout1", spout).each(allFields, new Debug("##### vehicles"));
    
    Stream slowVehiclesStream = vehiclesStream.min(new SpeedComparator()).each(vehicleField,
            new Debug("#### slowest vehicle"));
            
    Stream slowDriversStream = slowVehiclesStream.project(driverField).each(driverField,
            new Debug("##### slowest driver"));
            
    vehiclesStream.max(new SpeedComparator()).each(vehicleField, new Debug("#### fastest vehicle"))
            .project(driverField).each(driverField, new Debug("##### fastest driver"));
            
    vehiclesStream.minBy(Vehicle.FIELD_NAME, new EfficiencyComparator()).each(vehicleField,
            new Debug("#### least efficient vehicle"));
            
    vehiclesStream.maxBy(Vehicle.FIELD_NAME, new EfficiencyComparator()).each(vehicleField,
            new Debug("#### most efficient vehicle"));
            
    return topology.build();
}
 

public static FixedBatchSpout buildSpout() {
  List<Values> ticks = new FixedBatchSpoutBuilder().readData();
  FixedBatchSpout spout = new FixedBatchSpout(new Fields("stock-ticks"), 5, ticks.toArray(new Values[ticks.size()]));
  spout.setCycle(false);
  return spout;
}
 

public static StormTopology buildTopology(String hbaseRoot){
    Fields fields = new Fields("word", "count");
    FixedBatchSpout spout = new FixedBatchSpout(fields, 4,
            new Values("storm", 1),
            new Values("trident", 1),
            new Values("needs", 1),
            new Values("javadoc", 1)
    );
    spout.setCycle(true);

    TridentHBaseMapper tridentHBaseMapper = new SimpleTridentHBaseMapper()
            .withColumnFamily("cf")
            .withColumnFields(new Fields("word"))
            .withCounterFields(new Fields("count"))
            .withRowKeyField("word");

    HBaseValueMapper rowToStormValueMapper = new WordCountValueMapper();

    HBaseProjectionCriteria projectionCriteria = new HBaseProjectionCriteria();
    projectionCriteria.addColumn(new HBaseProjectionCriteria.ColumnMetaData("cf", "count"));

    HBaseState.Options options = new HBaseState.Options()
            .withConfigKey(hbaseRoot)
            .withDurability(Durability.SYNC_WAL)
            .withMapper(tridentHBaseMapper)
            .withProjectionCriteria(projectionCriteria)
            .withRowToStormValueMapper(rowToStormValueMapper)
            .withTableName("WordCount");

    StateFactory factory = new HBaseStateFactory(options);

    TridentTopology topology = new TridentTopology();
    Stream stream = topology.newStream("spout1", spout);

    stream.partitionPersist(factory, fields,  new HBaseUpdater(), new Fields());

    TridentState state = topology.newStaticState(factory);
    stream = stream.stateQuery(state, new Fields("word"), new HBaseQuery(), new Fields("columnName","columnValue"));
    stream.each(new Fields("word","columnValue"), new PrintFunction(), new Fields());
    return topology.build();
}
 

public static StormTopology buildTopology(LocalDRPC drpc) {
    FixedBatchSpout spout = new FixedBatchSpout(new Fields("sentence"), 3,
            new Values("the cow jumped over the moon"),
            new Values("the man went to the store and bought some candy"),
            new Values("four score and seven years ago"), new Values("how many apples can you eat"),
            new Values("to be or not to be the person"),
            new Values("marry had a little lamb whos fleese was white as snow"),
            new Values("and every where that marry went the lamb was sure to go"),
            new Values("one two three four five six seven eight nine ten"),
            new Values("this is a test of the emergency broadcast system this is only a test"),
            new Values("peter piper picked a peck of pickeled peppers"),
            new Values("JStorm is a distributed and fault-tolerant realtime computation system."),
            new Values(
                    "Inspired by Apache Storm, JStorm has been completely rewritten in Java and provides many more enhanced features."),
            new Values("JStorm has been widely used in many enterprise environments and proved robust and stable."),
            new Values("JStorm provides a distributed programming framework very similar to Hadoop MapReduce."),
            new Values(
                    "The developer only needs to compose his/her own pipe-lined computation logic by implementing the JStorm API"),
            new Values(" which is fully compatible with Apache Storm API"),
            new Values("and submit the composed Topology to a working JStorm instance."),
            new Values("Similar to Hadoop MapReduce, JStorm computes on a DAG (directed acyclic graph)."),
            new Values("Different from Hadoop MapReduce, a JStorm topology runs 24 * 7"),
            new Values("the very nature of its continuity abd 100% in-memory architecture "),
            new Values(
                    "has been proved a particularly suitable solution for streaming data and real-time computation."),
            new Values("JStorm guarantees fault-tolerance."), new Values("Whenever a worker process crashes, "),
            new Values(
                    "the scheduler embedded in the JStorm instance immediately spawns a new worker process to take the place of the failed one."),
            new Values(" The Acking framework provided by JStorm guarantees that every single piece of data will be processed at least once.") );
    spout.setCycle(true);
    
    
    int spout_Parallelism_hint = JStormUtils.parseInt(conf.get(TOPOLOGY_SPOUT_PARALLELISM_HINT), 1);
    int split_Parallelism_hint = JStormUtils.parseInt(conf.get(TOPOLOGY_SPLIT_PARALLELISM_HINT), 2);
    int count_Parallelism_hint = JStormUtils.parseInt(conf.get(TOPOLOGY_COUNT_PARALLELISM_HINT), 2);
    
    TridentTopology topology = new TridentTopology();
    TridentState wordCounts = topology.newStream("spout1", spout).parallelismHint(spout_Parallelism_hint)
            .each(new Fields("sentence"), new Split(), new Fields("word")).parallelismHint(split_Parallelism_hint).groupBy(new Fields("word"))
            .persistentAggregate(new MemoryMapState.Factory(), new Count(), new Fields("count"))
            .parallelismHint(count_Parallelism_hint);
            
    return topology.build();
}